Advantech module targets edge IoT applications
- July 10, 2024
- Steve Rogerson
Taiwanese embedded computer company Advantech has introduced a Smarc 2.1 computer-on-module for edge IoT applications in autonomous mobile robots (AMRs), medical, surveillance, robotics and beyond.
The ROM-6881 uses Rockchip’s RK3588 and RK3588J chipsets, with eight-core processors and up to 6.0Tops of AI inference capability. The module also supports high-resolution video with 8K at 30fps video encoding and 8K at 60fps decoding, ensuring efficient, high-quality display and resolution.
The RK3588 has eight processing cores – four Arm Cortex-A76 and four Cortex-A55 – that can reach speeds up to 2.4GHz. All eight cores are built using an 8nm process, providing a 300% increase in performance over the previous RK3399 processor. This ensures more computing power for platform management and a diverse range of applications.
Designed for edge AI applications, the RK3588 integrates a 6Tops NPU accelerator, giving it AI computing capabilities. This simplifies various edge AI inference tasks, ensuring performance and flexibility for a wide array of applications.
The module’s integrated 3D GPU ensures efficient, high-quality 3D rendering and display of panoramic content. Additionally, it is equipped to handle four Mipi CSI cameras, two USB 3.0 and three USB 2.0 signals, enabling access to multiple cameras simultaneously. Moreover, the module has an array of display interfaces including HDMI, DP, LVDS/DSI and eDP for up to four screens. It is suitable for medical equipment such as endoscopes, haemodialysis and AI-based in vitro diagnostics (IVD) systems.
Industrial robots and automated guided vehicles (AGVs) often demand high data throughput, low latency, low power consumption and cost efficiency. The modules has various interfaces including two gigabit ports, two USB 3.0 ports, three USB 2.0 ports, Sata and uarts, making it simple to integrate peripherals such as lidar, motors, IMUs and cameras to increase AMR efficiency. Moreover, the four PCIe 3.0 slots provide flexible expansion, allowing for enhancements in wired networks and the addition of FPGA, Wifi 6 and 5G modules.
The module supports multiple operating systems, including Debian and Android. To facilitate edge AI development, users can leverage the RKNN toolkit developed by Rockchip (www.rock-chips.com). This handles AI model conversions as well as inference and performance within an Ubuntu PC environment. For robotics applications, the ROM-6881 (www.advantech.com/en/products/77b59009-31a9-4751-bee1-45827a844421/rom-6881/mod_65b12594-2c3b-400b-b386-ed97aeb47852) runs the ROS2 operating system, providing a flexible framework for development of robotic applications.
Advantech (www.advantech.com) specialises in IoT intelligent systems and embedded platforms. To embrace the trends of IoT, big data and artificial intelligence, it promotes IoT hardware and software with the Wise-PaaS industrial IoT platform.